Model comparison
C4ai Aya Expanse 32b vs Mistral
C4ai Aya Expanse 32b is the stronger model overall, scoring 35.9 to 29.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Cohere
Mistral AISummary
- They share 17 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 8 categories and Mistral in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where C4ai Aya Expanse 32b leads 33.2 to 16.6.
- C4ai Aya Expanse 32b has downloadable open weights; the other is API-only.
Side by side
| C4ai Aya Expanse 32b | Mistral | |
|---|---|---|
| Provider | Cohere | Mistral AI |
| Noometry Index | 35.9 | 29.9 |
| Released | 2024-10-24 | — |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 34.8 (#231), Mistral: 33.8 (#250)
| Benchmark | C4ai Aya Expanse 32b | Mistral |
|---|---|---|
| LMArena Coding | 1197 | 1162 |
Reasoning C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 23.3 (#180), Mistral: 22.2 (#200)
| Benchmark | C4ai Aya Expanse 32b | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1193 | 1149 |
Math C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 34.0 (#197), Mistral: 22.3 (#278)
| Benchmark | C4ai Aya Expanse 32b | Mistral |
|---|---|---|
| LMArena Math | 1200 | 1180 |
| Omni-MATH | — | 7.2% |
Knowledge C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 33.2 (#206), Mistral: 16.6 (#288)
| Benchmark | C4ai Aya Expanse 32b | Mistral |
|---|---|---|
| LMArena Expert | 1182 | 1125 |
| MMLU-Pro | — | 27.7% |
| Vectara Hallucination Rate | 10.9% | — |
| GPQA (HELM) | — | 30.3% |
Multilingual C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 38.4 (#230), Mistral: 32.8 (#254)
| Benchmark | C4ai Aya Expanse 32b | Mistral |
|---|---|---|
| LMArena Non-English | 1213 | 1129 |
| LMArena Chinese | 1211 | 1109 |
| LMArena French | 1248 | 1180 |
| LMArena German | 1199 | 1155 |
| LMArena Japanese | 1163 | 1013 |
| LMArena Korean | 1158 | 1032 |
| LMArena Russian | 1227 | 1168 |
| LMArena Spanish | 1193 | 1143 |
Instruction Following C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 62.6 (#237), Mistral: 52.6 (#288)
| Benchmark | C4ai Aya Expanse 32b | Mistral |
|---|---|---|
| LMArena Instruction Following | 1196 | 1152 |
| IFEval | — | 56.8% |
Long Context C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 37.2 (#220), Mistral: 35.0 (#245)
| Benchmark | C4ai Aya Expanse 32b | Mistral |
|---|---|---|
| LMArena Longer Query | 1228 | 1153 |
Writing & Preference C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 42.2 (#235), Mistral: 37.0 (#260)
| Benchmark | C4ai Aya Expanse 32b | Mistral |
|---|---|---|
| LMArena Text | 1224 | 1165 |
| LMArena Creative Writing | 1200 | 1158 |
| LMArena Multi-Turn | 1190 | 1147 |
| WildBench | — | 66% |
Frequently asked questions
Is C4ai Aya Expanse 32b better than Mistral?
C4ai Aya Expanse 32b is the stronger model overall, scoring 35.9 to 29.9 on the Noometry Index.
Is C4ai Aya Expanse 32b or Mistral better for coding?
C4ai Aya Expanse 32b scores higher on coding benchmarks: 34.8 versus 33.8 in the Noometry coding category.
How many benchmarks do C4ai Aya Expanse 32b and Mistral share?
17 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Mistral has 22.